Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    calculated, fair, valuable, benefits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     کمپنی
    0.42
     довольно
    0.40
     সবচেয়ে
    0.40
     സ്വന്ത
    0.39
     কতকগুলি
    0.39
     উপজে
    0.38
     सहित
    0.38
    ontiti
    0.38
    ⒏
    0.38
    inda
    0.37
    POSITIVE LOGITS
    过程中
    0.50
     инстру
    0.45
     INSTR
    0.43
    ()=>{
    0.42
     =
    0.40
    /
    0.40
     경우
    0.40
     node
    0.40
    0.40
    对应的
    0.39
    Act Density 0.008%

    No Known Activations